Received-SPF: pass (google.com: domain of linux-kernel+bounces-185087-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Message-ID: <872f0ebd-124e-4a39-987c-ef9c273f1957@suse.de>
Date: Tue, 21 May 2024 16:23:53 +0200
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v3 1/1] nvme: multipath: Implemented new iopolicy
 "queue-depth"
To: John Meneghini <jmeneghi@redhat.com>, kbusch@kernel.org, hch@lst.de,
 sagi@grimberg.me, emilne@redhat.com
Cc: linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org,
 jrani@purestorage.com, randyj@purestorage.com, hare@kernel.org
References: <20240520202045.427110-1-jmeneghi@redhat.com>
 <20240520202045.427110-2-jmeneghi@redhat.com>
 <f808fa46-e7c7-48e6-8c80-3d28efd0afec@suse.de>
 <595e5988-b94d-41ba-a233-f87aed55028d@redhat.com>
Content-Language: en-US
From: Hannes Reinecke <hare@suse.de>
In-Reply-To: <595e5988-b94d-41ba-a233-f87aed55028d@redhat.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit

On 5/21/24 15:58, John Meneghini wrote:
> On 5/21/24 02:46, Hannes Reinecke wrote:
>> On 5/20/24 22:20, John Meneghini wrote:
>>> From: "Ewan D. Milne" <emilne@redhat.com>
>>>
> ...
>>> Tested-by: Marco Patalano <mpatalan@redhat.com>
>>> Reviewed-by: Randy Jennings <randyj@redhat.com>
> 
> I need to fix this. Randy doesn't have a redhat.com email address... Cut 
> an paste error :-(
> 
>>> Tested-by: Jyoti Rani <jani@purestorage.com>
>>>
> ...
>>> +void nvme_subsys_iopolicy_update(struct nvme_subsystem *subsys, int 
>>> iopolicy)
>>> +{
>>> +    struct nvme_ctrl *ctrl;
>>> +    int old_iopolicy = READ_ONCE(subsys->iopolicy);
>>> +
>>> +    WRITE_ONCE(subsys->iopolicy, iopolicy);
>>> +
>>> +    mutex_lock(&nvme_subsystems_lock);
>>> +    list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
>>> +        atomic_set(&ctrl->nr_active, 0);
>>> +        nvme_mpath_clear_ctrl_paths(ctrl);
>>
>> You always reset the variables here, even if specified iopolicy is
>> the same than the currently active one.
>> I'd rather check if the iopolicy is different before changing the 
>> settings.
> 
> Yes, Keith pointed this out too.  This is actually a feature not a bug.  
> In situations were we want to "reset" the nr_active counters on all 
> controllers the user can simply set the queue-depth iopolicy a second 
> time.  I don't expect users to do this very often... they shouldn't be 
> changing IO policies back and forth too much... but the ability to 
> "reset" the nr_active counters during testing has been very helpful and 
> important to do.  So I'd like to keep this.  Moreover, this is NOT the 
> performance path. I don't see the point in making performance 
> optimizations in a code path that is run once a year.
> 
Please add a comment indicating that.
Just to make it clear that it's by design.

Cheers,

Hannes